Deterministic recipe verification engine — validates AI-generated recipes against master SOPs.
Connect Guardian Engine to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Deterministic recipe verification engine — validates AI-generated recipes against master SOPs. The guardian engine mcp server is what makes that connection.
Guardian is a hosted MCP server. No install, no API key, no Docker. Pick your client and paste the config.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Machine — actionable repair** — findings come with structured patches (and fix_recipe can apply them deterministically); your agent authors the rest andCursor — Open Settings → MCP Servers → Add new MCP server, then paste:Windsurf — The Windsurf tool exposed by this serververify_recipe — Verify a candidate recipe against a Guardian master spec. Returns a structured report with a strict PASSED/FAILED verdict (no scores) and detailedfix_recipe — Deterministically repair a candidate recipe against a master spec. Verifies, applies every machine-actionable patch the symbolic engine producedlist_dishes — List all master recipes Guardian can verify against, with rich metadata (slug, title, cuisine, region, aliases, complexity)get_master — Return the canonical master recipe for a dish — a pure knowledge-base lookup, no LLM. Enables compare-then-verify loops: fetch the master, diffcheck_safety — Master-independent safety checks for any recipe — no dish resolution or master spec required. Checks poultry internal-temperature safety (≥ 74check_allergens — Check an ingredient list for EU FIC 1169/2011 allergen presence, with a detailed audit trace mapping each ingredient to its Annex II allergen groupverify_dietary_claim — Verify that a recipe satisfies a dietary claim, returning a structured verdict with the specific offending ingredients — never a vague paraphraseBecause this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Guardian Engine's toolset — Machine, Cursor, Windsurf and 7 more — is a fair guide to whether it matches your workflow. It is maintained by dev.kaimeilabs; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Guardian Engine's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Machine | actionable repair** — findings come with structured patches (and fix_recipe can apply them deterministically); your agent authors the rest and re-verifies. |
| Cursor | Open **Settings → MCP Servers → Add new MCP server**, then paste: |
| Windsurf | The Windsurf tool exposed by this server. |
| verify_recipe | Verify a candidate recipe against a Guardian master spec. Returns a structured report with a strict PASSED/FAILED verdict (no scores) and detailed findings, each citing the rule it violated. The verdict is policy-driven: |
| fix_recipe | Deterministically repair a candidate recipe against a master spec. Verifies, applies every machine-actionable patch the symbolic engine produced (missing ingredients, quantities, temperatures, durations, cooking media, s |
| list_dishes | List all master recipes Guardian can verify against, with rich metadata (slug, title, cuisine, region, aliases, complexity). |
| get_master | Return the canonical master recipe for a dish — a pure knowledge-base lookup, no LLM. Enables **compare-then-verify** loops: fetch the master, diff it against your recipe, then call verify_recipe instead of verifying bli |
| check_safety | Master-independent safety checks for **any** recipe — no dish resolution or master spec required. Checks poultry internal-temperature safety (≥ 74 °C) and scans all ingredients against the 14 EU FIC 1169/2011 Annex II al |
| check_allergens | Check an ingredient list for EU FIC 1169/2011 allergen presence, with a detailed audit trace mapping each ingredient to its Annex II allergen group (entry numbers and labels included). |
| verify_dietary_claim | Verify that a recipe satisfies a dietary claim, returning a structured verdict with the specific offending ingredients — never a vague paraphrase. |
{
"mcpServers": {
"guardian": {
"url": "https://api.kaimeilabs.dev/mcp",
"transport": "streamable-http"
}
}
}Configuration as documented by the project. Restart the client after saving.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.